{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:39:34Z","timestamp":1759333174852,"version":"3.44.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/indin41052.2019.8972078","type":"proceedings-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T00:16:43Z","timestamp":1580429803000},"page":"1185-1191","source":"Crossref","is-referenced-by-count":1,"title":["Data Preparation for Data Mining in Chemical Plants using Big Data"],"prefix":"10.1109","author":[{"given":"Reuben","family":"Borrison","sequence":"first","affiliation":[{"name":"ABB Corporate Research Center,Germany"}]},{"given":"Benjamin","family":"Kloepper","sequence":"additional","affiliation":[{"name":"ABB Corporate Research Center,Germany"}]},{"given":"Jennifer","family":"Mullen","sequence":"additional","affiliation":[{"name":"ABB Corporate Research Center,Germany"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Dealing with Missing Data","author":"scheffer","year":"2002","journal-title":"Technical Report"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1177\/0049124100028003003","article-title":"Multiple Imputation for Missing Data","volume":"28","author":"allison","year":"2000","journal-title":"Sociological Methods & Research"},{"key":"ref12","article-title":"Maximum Likelihood from Incomplete Data via the EM Algorithm","volume":"1","author":"dempster","year":"1977","journal-title":"Technical Report"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.7.2.147"},{"key":"ref14","article-title":"THE COLLINEARITY PROBLEM IN LINEAR REGRESSION","volume":"3","author":"wold","year":"1984","journal-title":"THE PARTIAL LEAST SQUARES (PLS) APPROACH TO GENERALIZED INVERSES* Technical Report"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2004.08.020"},{"journal-title":"Principal Component Analysis","year":"2002","author":"jolliffe","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2006.05.030"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012526430-3\/50009-X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1993.10476339"},{"key":"ref4","article-title":"Beyond Accuracy: What Data Quality Means to Data Consumers","volume":"4","author":"wang","year":"1996","journal-title":"Technical Report"},{"key":"ref3","article-title":"Defining Software Architectures for Big Data Enabled Operator Support Systems","author":"kl\u00f6pper","year":"2016","journal-title":"Technical Report"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/269012.269021","article-title":"Examining data quality","volume":"41","author":"kumar tayi","year":"1998","journal-title":"Communications of the ACM"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/gji\/ggu246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7439(96)00007-X"},{"key":"ref7","article-title":"Data Quality Assessment","volume":"4ve","author":"pipino","year":"2002","journal-title":"Technical Report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2008.12.012"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"8713","DOI":"10.1021\/ie800386v","article-title":"Dealing with Irregular Data in Soft Sensors: Bayesian Method and Comparative Study","volume":"47","author":"khatibisepehr","year":"2008","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2007.07.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-1524(00)00046-9"},{"key":"ref22","article-title":"Soft Sensors for Monitoring and Control of Industrial Processes","author":"fortuna","year":"2007","journal-title":"Advances in Industrial Control"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(97)00262-7"},{"key":"ref24","first-page":"611","author":"borrison","year":"2018","journal-title":"Reusable Big Data System for Industrial Data Mining - A Case Study on Anomaly Detection in Chemical Plants"},{"key":"ref23","article-title":"Data Preparation in the Big Data Era Best Practices for Data Integration","author":"castanedo","year":"2015","journal-title":"Technical Report"},{"year":"0","key":"ref26","article-title":"Dask: Scalable analytics in Python"},{"key":"ref25","first-page":"114","article-title":"Determining What Individual SUS Scores Mean: Adding an Adjective Rating Scale","volume":"4","author":"bangor","year":"2009","journal-title":"Journal of Usability Studies"}],"event":{"name":"2019 IEEE 17th International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2019,7,22]]},"location":"Helsinki, Finland","end":{"date-parts":[[2019,7,25]]}},"container-title":["2019 IEEE 17th International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8961950\/8972012\/08972078.pdf?arnumber=8972078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:35:32Z","timestamp":1755714932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8972078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/indin41052.2019.8972078","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}